Search augmented llms fail to use evidence behind outdated answers
Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence
Computation and LanguageArtificial IntelligenceInformation Retrieval
Summary
Sometimes language models that use web search give old or outdated answers even when newer information is available online. The authors studied this by creating facts that changed after the models were trained. They found that models often rely only on search result snippets instead of reading the full source, causing them to ignore up-to-date information. Even when the models see evidence, they may still prefer their old knowledge in their final answers.
What this means in practice
- •For search engine developers: Improve language model integrations to ensure models access full source pages, reducing outdated answer generation.
- •For chatbot engineers: Design chatbot retrieval systems that encourage reading full retrieved documents to enhance answer accuracy and trustworthiness.
Authors
Owen Walters, Lihu Chen, Francesca Toni
Abstract
Web search allows LLMs to access up-to-date information, but it remains unclear why they sometimes produce outdated answers even when relevant evidence is available. To study this problem, we construct temporal facts whose values changed after the models' training cutoffs. We evaluate one proprietary model under deployed web search and six open-weight model configurations under controlled retrieval. We find that models often answer from search snippets without opening the source pages, which is associated with higher rates of outdated answers and unfaithful citations. Our controlled experiments and layer-wise analysis reveal a gap between the availability of evidence and its effective use. Even when retrieved evidence influences internal predictions, models may still favour outdated information in their final answers. We hope these findings will help advance research on the reliable use of retrieved evidence in search-augmented LLMs.